APLUX

Edge AI accelerator card

Rhino Boost Q86

Add local AI compute to an existing host

A QCS8625 accelerator card integrating LPDDR5X, UFS and an Ethernet controller. A dedicated adapter carrier and companion software add local model inference and video analytics to the host.

Rhino Boost Q86 front

60 TOPS

Maximum AI performance (INT8, dense)

12 GB + 128 GB

Standard LPDDR5X / UFS 3.1

47 × 64 mm

Card outline

PCIe Gen4 x2

Host interconnect resources

Add local AI compute to an existing host

Match the compute platform to your device tasks, models, peripherals and product form factor.

Dedicated memory and system storage

Standard 12 GB LPDDR5X and 128 GB UFS 3.1, with optional 16 / 24 GB memory. Confirm configurations for model deployment requirements.

Host and AI collaboration

PCIe, Ethernet and USB, together with an adapter carrier, drivers and communication services, connect the host to the on-card runtime.

Video analytics and model inference

CPU, Adreno 750, NPU and video engines support adapted vision, language and multimodal applications.

A dedicated card with a companion adapter

The 52-pin edge connector uses this product's own definition. Verify power, signals and cooling and use the adapter board for system integration.

From interface capabilities to device integration

Evaluate AI compute expansion against host links and connection definitions.

Functional overview; refer to the product specification for connector positions and electrical definitions.

PCIe

1 × PCIe 4.0 x2 through the dedicated edge connector

Explore integration paths for real-world tasks

Choose device workloads and integration paths based on platform capabilities and this model's interfaces.

Qualcomm QCS8625

Expand existing hosts with video AI analytics

Host collaborationVideo inferenceEvent analytics
Up to 60 TOPS(INT8, dense)Platform-rated peak; validate performance for your workload
Illustrative AI NVR

AI NVR

Combine multiple network video inputs, storage and recognition into a locally running intelligent video pipeline.

Platform fit
Offload model inference from host business processing, analyze video frames and return event results.
Host integration
The host handles video input, decoding and storage; the accelerator runs adapted inference workloads. Dedicated connection compatibility is required.
Video inputRecognition and analyticsEvent recording
View interfaces and integration
Illustrative AI analytics box

AI analytics box

Extend existing video systems and hosts, connecting AI analytical results to alerts, retrieval and business applications.

Platform fit
Act as an AI coprocessing node providing recognition and analytical results to existing business software.
Host integration
Adapt host data links through the dedicated 52-pin connection and return results to business software; this is not plug-and-play in a standard slot.
Existing video streamsAI analyticsBusiness integration
View interfaces and integration

Device images illustrate application directions; peripherals, enclosure design and software require project-specific integration.

Rhino Boost Q86 specifications

Configurations below follow the edge AI accelerator card documentation. Module capabilities and physically exposed device interfaces are distinguished.

Compute and storage

Rhino Boost Q86 · Compute and storage
Compute platformQualcomm QCS8625
Process4 nm
CPUOcta-core Qualcomm Kryo, up to 3.4 GHz
NPUQualcomm Hexagon
AI performance (INT8, dense)Up to 60 TOPS(INT8, dense)
AI performance (INT8, sparse)Up to 120 TOPS(INT8, sparse)
AI performance (FP16)Up to 15 TOPS(FP16)
GPUQualcomm Adreno
Standard memory12 GB LPDDR5X
Optional memory16 GB / 24 GB LPDDR5X, according to the order configuration
Storage128 GB UFS 3.1

AI figures are platform-rated peaks. Dense, sparse and FP16 figures are listed separately; actual performance depends on the model, precision, software and cooling. Input power ratings do not represent total board consumption. Accessories and system images depend on the delivered configuration.

Product configuration and integration notes

The dedicated 52-pin edge connector definition does not imply compatibility with arbitrary Mini-PCIe slots. Adapt the host data links and electrical connections accordingly.

60 TOPS refers to INT8 dense performance and 120 TOPS to INT8 sparse performance. Typical NPU inference power is not total card consumption.

Build your edge AI product with Rhino Boost Q86

Share your model, peripheral, mechanical and system requirements to define the product and delivery configuration together.